All MCQs

The correct answer is deep models usually contain multiple hidden layers. This matches the Deep Learning course topic: Shallow vs deep learning.

The correct answer is an autoencoder learns to encode input into a latent representation and reconstruct it. This matches the Deep Learning course topic: Autoencoders.

The correct answer is a gan trains a generator and discriminator in an adversarial setting. This matches the Deep Learning course topic: GANs.

The correct answer is a training set is used to fit model parameters. This matches the Deep Learning course topic: Training set.

The correct answer is sparse coding encourages representations where only a small number of units are active. This matches the Deep Learning course topic: Sparse coding.

The correct answer is data augmentation creates modified training examples to improve robustness. This matches the Deep Learning course topic: Data augmentation.

The correct answer is a test set estimates performance on unseen data. This matches the Deep Learning course topic: Test set.

The correct answer is a deep belief network is built using stacked probabilistic latent-variable layers. This matches the Deep Learning course topic: Deep belief networks.

The correct answer is data normalization scales or centers data to support stable training. This matches the Deep Learning course topic: Data normalization.

The correct answer is a validation set supports model selection and hyperparameter tuning. This matches the Deep Learning course topic: Validation set.

The correct answer is a restricted boltzmann machine has visible and hidden units with no connections within the same layer. This matches the Deep Learning course topic: RBM.

The correct answer is dropout randomly disables units during training to reduce co-adaptation. This matches the Deep Learning course topic: Dropout.